Loading packages

In [1]:
from genepy.utils import helper as h

# to comment in your case
from taigapy import TaigaClient
tc = TaigaClient()

from celligner import Celligner
import pandas as pd
# to comment in your case
from depmapomics import tracker as track
#autoreload
%load_ext autoreload
%autoreload 2
#output
from bokeh.plotting import output_notebook
output_notebook()

from celligner.params import TISSUE_COLOR
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7ff92c2d32f0>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
  - Of which 2 did not match due to:
  Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
    With argument(s): '(x=array(float32, 2d, A), axis=int64)':
   Rejected as the implementation raised a specific error:
     TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7ff92c2d32f0>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:29: NumbaPerformanceWarning: np.dot() is faster on contiguous arrays, called on (array(float32, 1d, A), array(float32, 1d, A))
  dist[i, j] = np.dot(m[i], n[j])
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:197: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "adjust_s_variance" failed type inference due to: NameError: name 'sq_dist_to_line' is not defined
  @jit(float32(float32[:, :], float32[:, :], float32[:], float32[:], float32), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:197: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "adjust_s_variance" failed type inference due to: Cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "celligner/mnnpy/mnnpy/utils.py", line 205:
def adjust_s_variance(data1, data2, curcell, curvect, sigma):
    <source elided>
    totalprob2 = 0.
    for samecell in data2:
    ^

  @jit(float32(float32[:, :], float32[:, :], float32[:], float32[:], float32), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "adjust_s_variance" was compiled in object mode without forceobj=True, but has lifted loops.

File "celligner/mnnpy/mnnpy/utils.py", line 199:
def adjust_s_variance(data1, data2, curcell, curvect, sigma):
    distance1 = np.zeros((data1.shape[0], 2), dtype=np.float32)
    ^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 199:
def adjust_s_variance(data1, data2, curcell, curvect, sigma):
    distance1 = np.zeros((data1.shape[0], 2), dtype=np.float32)
    ^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:197: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32(float32[:, :], float32[:, :], float32[:], float32[:], float32), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:236: NumbaPerformanceWarning: np.dot() is faster on contiguous arrays, called on (array(float32, 1d, C), array(float32, 1d, A))
  scale = np.dot(working, grad)
Loading BokehJS ...

Loading expression files

In [2]:
# load from taiga public (figshare link)
# load internal expression,
# latest version can be found at https://depmap.org/portal/download/
# can also be loaded like so pd.read_csv('gs://ccle_default_params/celligner_ex/CCLE_expression.csv.gz', index_col=0)
CCLE_expression = tc.get(name='internal-21q3-fe4c',
                         file='CCLE_expression_full')  


# load  TCGA expression
# this dataset was generated from  ,using this script: 
# caan be found here: pd.read_csv('gs://ccle_default_params/celligner_ex/TCGA_expression.csv.gz', index_col=0)
TCGA_expression = tc.get(name='celligner-input-9827',
                         file='tumor_expression')
No dataset version provided. Using version 16.
No dataset version provided. Using version 1.
In [3]:
# subset gene names to ensembl ids only
CCLE_expression = CCLE_expression[CCLE_expression.columns[:-92]]
CCLE_expression.columns = list(map(lambda x: x.split(
    ' (')[1][:-1] if ' (' in x else x, CCLE_expression.columns))

common = set(CCLE_expression.columns).intersection(
    set(TCGA_expression.columns))
CCLE_expression = CCLE_expression[list(common)]
TCGA_expression = TCGA_expression[list(common)]

Managing annotations

In [5]:
# loading annotations
CCLE_annotation = track.getTracker() # the function uses pygsheets to load this: REFSHEET_URL=https://docs.google.com/spreadsheets/d/1Pgb5fIClGnErEqzxpU7qqX6ULpGTDjvzWwDN8XUJKIY
# Sheets.from_files(MY_ID, MYSTORAGE_ID).get(REFSHEET_URL).sheets[0].to_frame(index_col=0)
# you can also get it from pd.read_csv('gs://ccle_default_params/celligner_ex/CCLE_annotation.csv.gz', index_col=0)


# can be loaded from 
# pd.read_csv('gs://ccle_default_params/celligner_ex/TCGA_annotation.csv.gz', index_col=0)
TCGA_annotation = tc.get(name='celligner-input-9827',
                         file='tumor_annotations') # generated manually 
No dataset version provided. Using version 1.
In [6]:
# transforming annotations
CCLE_annotation = CCLE_annotation.drop_duplicates('arxspan_id').set_index("arxspan_id")
CCLE_annotation = CCLE_annotation.loc[CCLE_expression.index, ["origin", 'subtype']].rename(columns={"origin": "tissue_type", "subtype": 'disease_type'})
CCLE_annotation["cell_type"] = "cancer cell line"

TCGA_annotation = TCGA_annotation.set_index("sampleID").loc[TCGA_expression.index,["lineage",
"subtype"]].rename(columns={"lineage":"tissue_type", "subtype": 'disease_type'})
TCGA_annotation['cell_type'] = "tumor sample"
In [81]:
# some name are not consistent between the two datasets
rename = {np.nan: "unknown", "adrenal_cortex": "adrenal", "colorectal": "colon", 'thymus': 'thyroid', 'meninges':"central_nervous_system", None: "unknown", 'brain': "central_nervous_system"}
CCLE_annotation = CCLE_annotation.replace({"tissue_type": rename})
TCGA_annotation = TCGA_annotation.replace({"tissue_type": rename})
[autoreload of celligner failed: Traceback (most recent call last):
  File "/home/jeremie/miniconda3/lib/python3.7/site-packages/IPython/extensions/autoreload.py", line 245, in check
    superreload(m, reload, self.old_objects)
  File "/home/jeremie/miniconda3/lib/python3.7/site-packages/IPython/extensions/autoreload.py", line 394, in superreload
    module = reload(module)
  File "/home/jeremie/miniconda3/lib/python3.7/imp.py", line 314, in reload
    return importlib.reload(module)
  File "/home/jeremie/miniconda3/lib/python3.7/importlib/__init__.py", line 169, in reload
    _bootstrap._exec(spec, module)
  File "<frozen importlib._bootstrap>", line 630, in _exec
  File "<frozen importlib._bootstrap_external>", line 724, in exec_module
  File "<frozen importlib._bootstrap_external>", line 860, in get_code
  File "<frozen importlib._bootstrap_external>", line 791, in source_to_code
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/home/jeremie/celligner/celligner/__init__.py", line 729
    for val in
              ^
SyntaxError: invalid syntax
]
[autoreload of celligner.params failed: Traceback (most recent call last):
  File "/home/jeremie/miniconda3/lib/python3.7/site-packages/IPython/extensions/autoreload.py", line 245, in check
    superreload(m, reload, self.old_objects)
  File "/home/jeremie/miniconda3/lib/python3.7/site-packages/IPython/extensions/autoreload.py", line 394, in superreload
    module = reload(module)
  File "/home/jeremie/miniconda3/lib/python3.7/imp.py", line 314, in reload
    return importlib.reload(module)
  File "/home/jeremie/miniconda3/lib/python3.7/importlib/__init__.py", line 169, in reload
    _bootstrap._exec(spec, module)
  File "<frozen importlib._bootstrap>", line 630, in _exec
  File "<frozen importlib._bootstrap_external>", line 724, in exec_module
  File "<frozen importlib._bootstrap_external>", line 860, in get_code
  File "<frozen importlib._bootstrap_external>", line 791, in source_to_code
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/home/jeremie/celligner/celligner/params.py", line 4
    'other',
           ^
SyntaxError: invalid syntax
]

Fitting celliner with the CCLE dataset

In [ ]:
# issues when rerunning celligner
In [17]:
my_alligner = Celligner(make_plots=True, priotize_fit=True)
my_alligner.fit(CCLE_expression, CCLE_annotation)
fetching gene names from biomart cache
using only usefull genes
looking at 1411 samples.
found 29593 common genes
creating a fit dataset..
reducing dimensionality...
clustering...
WARNING: You’re trying to run this on 29593 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
doing differential expression analysis on the clusters
running differential expression on 34 clusters
running limmapy on the samples
you need to have R installed with the limma library installed
3.4.5
done
Out[17]:
<celligner.Celligner at 0x7f2d848adf98>
In [10]:
# running with regular mnn
my_alligner.method = "mnn"
_ = my_alligner.transform(TCGA_expression, TCGA_annotation)
looking at 12236 samples.
found 29593 common genes
creating a transform input..
reducing dimensionality...
clustering..
WARNING: You’re trying to run this on 70 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
doing differential expression analysis on the clusters..
running differential expression on 58 clusters
running limmapy on the samples
you need to have R installed with the limma library installed
3.4.5
there is 0.398 overlap between the fit and transform dataset in their most variable genes
doing cPCA..
transform
regressing out the cPCA components..
doing the MNN analysis using scanPy MNN...
Performing cosine normalization...
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7ffb24068598>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
    - Of which 2 did not match due to:
    Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
      With argument(s): '(x=array(float32, 2d, A), axis=int64)':
     Rejected as the implementation raised a specific error:
       TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7ffb24068598>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7ffb24068598>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
    - Of which 2 did not match due to:
    Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
      With argument(s): '(x=array(float32, 2d, A), axis=int64)':
     Rejected as the implementation raised a specific error:
       TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7ffb24068598>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
Starting MNN correct iteration. Reference batch: 0
Step 1 of 1: processing batch 1
  Looking for MNNs...
found 10135 mnns..
  Computing correction vectors...
  Adjusting variance...
  Applying correction...
MNN correction complete. Gathering output...
done
reducing dimensionality...
> /home/jeremie/celligner/celligner/__init__.py(630)plot()
    629     import ipdb; ipdb.set_trace()
--> 630     if 'colors' not in plot_kwargs:
    631       if show_clusts:

ipdb> c
[1, 1, 1, 1, 1, 1, 1, 1, 1]
making plot...
In [29]:
# running with regular mnn
my_alligner.method = "mnn"
_ = my_alligner.transform(_rerun=False)
reducing dimensionality...
doing differential expression analysis on the clusters..
regressing out the cPCA components..
doing the MNN analysis using scanPy MNN...
Performing cosine normalization...
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7f48a80eaa60>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
    - Of which 2 did not match due to:
    Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
      With argument(s): '(x=array(float32, 2d, A), axis=int64)':
     Rejected as the implementation raised a specific error:
       TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7f48a80eaa60>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7f48a80eaa60>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
    - Of which 2 did not match due to:
    Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
      With argument(s): '(x=array(float32, 2d, A), axis=int64)':
     Rejected as the implementation raised a specific error:
       TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7f48a80eaa60>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
Starting MNN correct iteration. Reference batch: 0
Step 1 of 1: processing batch 1
  Looking for MNNs...
found 10136 mnns..
  Computing correction vectors...
  Adjusting variance...
  Applying correction...
MNN correction complete. Gathering output...
done
reducing dimensionality...
making plot...
In [13]:
my_alligner.umap_kwargs
Out[13]:
{'n_neighbors': 10, 'min_dist': 0.5, 'metric': 'euclidean', 'n_components': 2}
In [31]:
my_alligner.plot(color_column="tissue_type", colortable=TISSUE_COLOR, umap_kwargs={'n_neighbors': 15,'min_dist': 0.2, 'metric': 'cosine'})
reducing dimensionality...
making plot...
Out[31]:
Figure(
id = '6215', …)
In [28]:
my_alligner.plot(rerun=False)
making plot...
Out[28]:
Figure(
id = '4816', …)
In [ ]:
my_alligner.neightbors_kwargs
In [18]:
# using the marioni mnn method
my_alligner.method = "mnn_marioni"
my_alligner.mnn_kwargs = {'k1': 5, 'k2': 50, 'cosine_norm': True, "fk":5}
_ = my_alligner.transform(TCGA_expression, TCGA_annotation)
looking at 12236 samples.
found 29593 common genes
creating a transform input..
reducing dimensionality...
clustering..
WARNING: You’re trying to run this on 70 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
doing differential expression analysis on the clusters..
running differential expression on 57 clusters
running limmapy on the samples
you need to have R installed with the limma library installed
3.4.5
there is 0.329 overlap between the fit and transform dataset in their most variable genes
> /home/jeremie/celligner/celligner/__init__.py(416)transform()
    415       # doing cPCA on the dataset
--> 416       print('doing cPCA..')
    417       # TODO: try the automated version, (select the best alpha above 1?)

ipdb> c
doing cPCA..
transform
regressing out the cPCA components..
doing the MNN analysis using Marioni et al. method..
Performing cosine normalization...
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7f2e97d29a60>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
    - Of which 2 did not match due to:
    Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
      With argument(s): '(x=array(float32, 2d, A), axis=int64)':
     Rejected as the implementation raised a specific error:
       TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7f2e97d29a60>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "l2_norm" failed type inference due to: No implementation of function Function(<function norm at 0x7f2e97d29a60>) found for signature:
 
 >>> norm(x=array(float32, 2d, A), axis=Literal[int](1))
 
There are 2 candidate implementations:
    - Of which 2 did not match due to:
    Overload in function 'norm_impl': File: numba/np/linalg.py: Line 2352.
      With argument(s): '(x=array(float32, 2d, A), axis=int64)':
     Rejected as the implementation raised a specific error:
       TypeError: norm_impl() got an unexpected keyword argument 'x'
  raised from /home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/typing/templates.py:722

During: resolving callee type: Function(<function norm at 0x7f2e97d29a60>)
During: typing of call at /home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py (16)


File "celligner/mnnpy/mnnpy/utils.py", line 16:
def l2_norm(in_matrix):
    return np.linalg.norm(x=in_matrix, axis=1)
    ^

  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:152: NumbaWarning: Function "l2_norm" was compiled in object mode without forceobj=True.

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/miniconda3/lib/python3.7/site-packages/numba/core/object_mode_passes.py:162: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "celligner/mnnpy/mnnpy/utils.py", line 15:
@jit(float32[:](float32[:, :]), nogil=True)
def l2_norm(in_matrix):
^

  state.func_ir.loc))
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
/home/jeremie/celligner/celligner/mnnpy/mnnpy/utils.py:14: NumbaWarning: Code running in object mode won't allow parallel execution despite nogil=True.
  @jit(float32[:](float32[:, :]), nogil=True)
  Looking for MNNs...
  Found 10906 mutual nearest neighbors.
done
reducing dimensionality...
making plot...
In [22]:
my_alligner.plot(color_column="tissue_type", colortable=TISSUE_COLOR, umap_kwargs={'n_neighbors': 10,'min_dist': 0.2, 'metric': 'euclidean'})
reducing dimensionality...
making plot...
Out[22]:
Figure(
id = '3067', …)
In [52]:
my_alligner.save('../temp/demo/')
-------------------------------------------------
PicklingError   Traceback (most recent call last)
<ipython-input-52-d7b272fd5fed> in <module>
----> 1 my_alligner.save('../temp/demo/')

~/celligner/celligner/__init__.py in save(self, folder, asData)
    525     if not asData:
    526       with open(os.path.join(folder, 'model.pkl'), 'wb') as f:
--> 527         pickle.dump(self, f)
    528       # save the data
    529     else:

PicklingError: Can't pickle <class 'celligner.Celligner'>: it's not the same object as celligner.Celligner

adding other datasets to celligner

In [48]:
# you can load the dataset from gcp: (you can do so by hand or by installing gsutil)
# (make sure you have the right folder and then do:
# ! gsutil cp gs://ccle_default_params/cellinger_ex/model.pkl ../temp/demo/
my_alligner = Celligner()
my_alligner.load('../temp/demo/')
fetching gene names from biomart cache
using only usefull genes
In [3]:
# met500 
met500_ann = tc.get(name='met500-fc3c', file='met500_ann')
met500_meta = tc.get(name='met500-fc3c', file='met500_meta')
met500_TPM = tc.get(name='met500-fc3c', file='met500_TPM') #20,979x868 matrix

#Novartis_PDX
Novartis_PDX_ann = tc.get(name='pdx-data-3d29', file='Novartis_PDX_ann')
Novartis_PDX_TPM = tc.get(name='pdx-data-3d29', file='Novartis_PDX_TPM').T # 38,087x445

#pediatric_PDX
pediatric_PDX_ann = tc.get(name='pdx-data-3d29', file='pediatric_PDX_ann')
pediatric_PDX_TPM = tc.get(name='pdx-data-3d29', file='pediatric_PDX_TPM') #80,000x250
No dataset version provided. Using version 1.
No dataset version provided. Using version 1.
No dataset version provided. Using version 1.
No dataset version provided. Using version 2.
No dataset version provided. Using version 2.
No dataset version provided. Using version 2.
No dataset version provided. Using version 2.
In [4]:
met500_meta["primary_site"] = met500_ann['primary_site'].values
del met500_ann
met500_ann = met500_meta.rename(columns={"Sample_id": 'sample_id', 'tissue': 'tissue_type', 'primary_site': "disease_type", "type": "cell_type"}).set_index('sample_id', drop=True)[["tissue_type","disease_type","cell_type"]].replace({"tissue_type":rename})
In [5]:
pediatric_PDX_ann = pediatric_PDX_ann.rename(columns={"sampleID": 'sample_id', 'lineage': 'tissue_type', 'subtype': "disease_type", "type": "cell_type"}).set_index('sample_id', drop=True)[['cell_type', 'disease_type', 'tissue_type']].replace({"tissue_type":rename})
In [6]:
Novartis_PDX_ann = Novartis_PDX_ann.rename(columns={"sampleID": 'sample_id', 'lineage': 'tissue_type', 'subtype': "disease_type", "type": "cell_type"}).set_index('sample_id', drop=True)[['cell_type', 'disease_type', 'tissue_type']].replace({"tissue_type":rename})
In [9]:
import seaborn as sns
sns.heatmap(pd.concat([pediatric_PDX_TPM.loc[:,set(pediatric_PDX_TPM.columns) & set(Novartis_PDX_TPM.columns)], Novartis_PDX_TPM.loc[:,set(pediatric_PDX_TPM.columns) & set(Novartis_PDX_TPM.columns)]]).T.corr())
Out[9]:
<AxesSubplot:>
In [53]:
# if you want to align to both CCLE and TCGA, you can ask celligner to consider the two (fit + _pre-transformed_ transform datasets) as a fit dataset by calling:
# my_alligner.putAllToFit()

# you can add your dataset as a dataset to be aligned to, by puting it in fit:
# my_alligner.addToFit(yourdataset).transform()
# /!\ need to already have a transform dataset (if you loaded the example model, this is TCGA)

# you can add your dataset as one to align, by putting it in transform:
# my_alligner.addToTransform(yourdataset)
# /!\ need to already have a fit dataset (if you loaded the example model, this is CCLE)

# if your dataset is small enough it might actually not work well to put it in transform it seems!
# if your dataset is small and similar enough, you can add the parameter dotransform=False (or dofit=False) so that it doesn't fully retransforms or refit but uses cached computation instead.
my_alligner.priotize_fit=False
my_alligner.putAllToFit(redo_diff=False)
_ = my_alligner.transform(met500_TPM, met500_ann, recompute_contamination=False)
clustering...
WARNING: You’re trying to run this on 29593 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
done
looking at 868 samples.
found 18218 common genes
creating a transform input..
clustering..
WARNING: You’re trying to run this on 18218 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
reducing dimensionality...
doing differential expression analysis on the clusters..
running differential expression on 35 clusters
running limmapy on the samples
you need to have R installed with the limma library installed
3.4.5
there is 0.235 overlap between the fit and transform dataset in their most variable genes
regressing out the cPCA components..
doing the MNN analysis using Marioni et al. method..
Performing cosine normalization...
  Looking for MNNs...
  Found 3713 mutual nearest neighbors.
done
reducing dimensionality...
making plot...
Out[53]:
(                                 ENSG00000229665  ENSG00000139970  \
 ES_5001-capt-SI_5013-C0LAMACXX          0.009057         0.755419   
 ES_5004-capt-SI_5834-C19KEACXX          0.079653        -0.522041   
 ES_5004-poly-SI_5767-C19KEACXX          0.020171        -0.804300   
 ES_5005-capt-SI_5505-D130HACXX         -0.005608         5.168651   
 ES_5005-poly-SI_5486-D12YGACXX         -0.001901         4.351374   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         0.003279         2.097418   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.011900        -0.973947   
 TP_2131-capt-SI_11906-C7F4VANXX         0.000935        -0.571228   
 TP_2141-capt-SI_12056-H53C5ADXX         0.041927        -1.088706   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.002092         4.204988   
 
                                  ENSG00000181754  ENSG00000185507  \
 ES_5001-capt-SI_5013-C0LAMACXX          0.616676        -0.796573   
 ES_5004-capt-SI_5834-C19KEACXX          0.042335         0.448864   
 ES_5004-poly-SI_5767-C19KEACXX         -1.141447        -1.833207   
 ES_5005-capt-SI_5505-D130HACXX         -0.097001         0.565141   
 ES_5005-poly-SI_5486-D12YGACXX          0.063535         0.188562   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         0.909413         0.234904   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.241607         0.305689   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.126598         0.354367   
 TP_2141-capt-SI_12056-H53C5ADXX         0.415384        -0.025494   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.631829        -1.295765   
 
                                  ENSG00000151790  ENSG00000244623  \
 ES_5001-capt-SI_5013-C0LAMACXX          0.756919         0.007529   
 ES_5004-capt-SI_5834-C19KEACXX         -0.478666         0.137162   
 ES_5004-poly-SI_5767-C19KEACXX          3.099329         0.800424   
 ES_5005-capt-SI_5505-D130HACXX         -1.387106        -0.057230   
 ES_5005-poly-SI_5486-D12YGACXX         -1.055097        -0.048710   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         1.541525         0.167493   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.728589         0.011243   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.202375         0.057435   
 TP_2141-capt-SI_12056-H53C5ADXX         0.714452        -0.079891   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.241180         0.072492   
 
                                  ENSG00000186951  ENSG00000165496  \
 ES_5001-capt-SI_5013-C0LAMACXX         -1.384283        -0.277787   
 ES_5004-capt-SI_5834-C19KEACXX          0.820176         0.037447   
 ES_5004-poly-SI_5767-C19KEACXX          0.508045         0.459195   
 ES_5005-capt-SI_5505-D130HACXX         -0.496636         0.122281   
 ES_5005-poly-SI_5486-D12YGACXX         -0.868545         0.032793   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -0.196875         0.392018   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.566015        -0.079536   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.305369        -0.094815   
 TP_2141-capt-SI_12056-H53C5ADXX         0.046453        -0.308889   
 TP_2156-capt-SI_12477-C7G91ANXX         0.228639         0.007876   
 
                                  ENSG00000158716  ENSG00000108417  ...  \
 ES_5001-capt-SI_5013-C0LAMACXX          0.913309         0.405645  ...   
 ES_5004-capt-SI_5834-C19KEACXX         -0.157262         1.010369  ...   
 ES_5004-poly-SI_5767-C19KEACXX         -0.242821         0.489920  ...   
 ES_5005-capt-SI_5505-D130HACXX          1.956578        -0.600420  ...   
 ES_5005-poly-SI_5486-D12YGACXX          2.002360        -0.182836  ...   
 ...                                          ...              ...  ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -1.474862        -0.164041  ...   
 TP_2130-capt-SI_11905-C7FMDANXX         1.151907         0.222681  ...   
 TP_2131-capt-SI_11906-C7F4VANXX         1.080469         0.055891  ...   
 TP_2141-capt-SI_12056-H53C5ADXX         1.768405        -0.269647  ...   
 TP_2156-capt-SI_12477-C7G91ANXX         2.362499        -0.772788  ...   
 
                                  ENSG00000105088  ENSG00000136738  \
 ES_5001-capt-SI_5013-C0LAMACXX          2.283852        -0.301929   
 ES_5004-capt-SI_5834-C19KEACXX         -0.583657        -0.219657   
 ES_5004-poly-SI_5767-C19KEACXX         -2.652403         1.741222   
 ES_5005-capt-SI_5505-D130HACXX          0.596760        -0.682071   
 ES_5005-poly-SI_5486-D12YGACXX          0.449245        -0.723488   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -1.772989        -0.445764   
 TP_2130-capt-SI_11905-C7FMDANXX        -1.517982         0.534567   
 TP_2131-capt-SI_11906-C7F4VANXX        -2.190997        -0.170856   
 TP_2141-capt-SI_12056-H53C5ADXX         1.776177         0.068475   
 TP_2156-capt-SI_12477-C7G91ANXX        -1.326375        -0.822000   
 
                                  ENSG00000142235  ENSG00000143952  \
 ES_5001-capt-SI_5013-C0LAMACXX          0.736861        -0.182244   
 ES_5004-capt-SI_5834-C19KEACXX         -0.091436        -0.334147   
 ES_5004-poly-SI_5767-C19KEACXX         -1.452678         0.954550   
 ES_5005-capt-SI_5505-D130HACXX         -0.897127         0.288552   
 ES_5005-poly-SI_5486-D12YGACXX         -0.946484        -0.311679   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -1.177888        -0.214526   
 TP_2130-capt-SI_11905-C7FMDANXX         0.012539        -0.174808   
 TP_2131-capt-SI_11906-C7F4VANXX         0.018638         0.058551   
 TP_2141-capt-SI_12056-H53C5ADXX        -0.022322        -0.676249   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.495633         1.077309   
 
                                  ENSG00000161714  ENSG00000169800  \
 ES_5001-capt-SI_5013-C0LAMACXX         -0.557463        -0.014084   
 ES_5004-capt-SI_5834-C19KEACXX          1.700649        -0.016119   
 ES_5004-poly-SI_5767-C19KEACXX         -0.702025         0.008427   
 ES_5005-capt-SI_5505-D130HACXX         -2.800869        -0.023556   
 ES_5005-poly-SI_5486-D12YGACXX         -2.484525        -0.018098   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         2.088491        -0.013928   
 TP_2130-capt-SI_11905-C7FMDANXX         2.029802        -0.034686   
 TP_2131-capt-SI_11906-C7F4VANXX         0.398697        -0.035416   
 TP_2141-capt-SI_12056-H53C5ADXX        -0.039405        -0.024161   
 TP_2156-capt-SI_12477-C7G91ANXX        -4.125488        -0.019349   
 
                                  ENSG00000148824  ENSG00000120705  \
 ES_5001-capt-SI_5013-C0LAMACXX         -0.529426        -1.115863   
 ES_5004-capt-SI_5834-C19KEACXX         -0.679389         0.601288   
 ES_5004-poly-SI_5767-C19KEACXX         -4.388516         0.490267   
 ES_5005-capt-SI_5505-D130HACXX          0.884433        -0.075051   
 ES_5005-poly-SI_5486-D12YGACXX          0.571261        -0.564766   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         0.267123         0.183217   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.563423         0.117468   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.318430         0.060895   
 TP_2141-capt-SI_12056-H53C5ADXX        -0.025030         0.446102   
 TP_2156-capt-SI_12477-C7G91ANXX         0.246973        -0.563621   
 
                                  ENSG00000112378  ENSG00000241322  
 ES_5001-capt-SI_5013-C0LAMACXX          0.751524         0.131805  
 ES_5004-capt-SI_5834-C19KEACXX          1.112102         0.533137  
 ES_5004-poly-SI_5767-C19KEACXX          1.912054         0.674721  
 ES_5005-capt-SI_5505-D130HACXX          0.253184        -1.360741  
 ES_5005-poly-SI_5486-D12YGACXX         -0.662172        -1.003261  
 ...                                          ...              ...  
 TP_2123-poly-SI_11689-C7G60ANXX        -0.438502         0.549056  
 TP_2130-capt-SI_11905-C7FMDANXX         2.071235         1.564062  
 TP_2131-capt-SI_11906-C7F4VANXX         3.676588         2.140582  
 TP_2141-capt-SI_12056-H53C5ADXX         1.383039         0.402192  
 TP_2156-capt-SI_12477-C7G91ANXX         1.935112        -0.856332  
 
 [868 rows x 18218 columns],
                  ENSG00000229665  ENSG00000139970  ENSG00000181754  \
 ACH-001113             -0.012122         0.695668         0.914510   
 ACH-001289             -0.012122         3.368767         1.480198   
 ACH-001339              0.002233        -0.996209        -0.405730   
 ACH-001538             -0.012122        -1.024224         0.300539   
 ACH-000242             -0.012122        -1.024224        -0.284424   
 ...                          ...              ...              ...   
 TCGA-95-7947-01        -0.047118        -1.890201        -0.269406   
 TCGA-VQ-AA6F-01         0.000357        -0.136730        -0.685209   
 TCGA-BR-8588-01         0.004822        -1.841184        -0.254086   
 TCGA-24-2254-01        -0.012013        -0.064373        -0.299324   
 TCGA-DD-A115-01        -0.001574        -1.827779        -0.290696   
 
                  ENSG00000185507  ENSG00000151790  ENSG00000244623  \
 ACH-001113             -0.160200        -0.652990         0.205861   
 ACH-001289             -2.859583        -0.748749        -0.045101   
 ACH-001339              0.880471         0.927554        -0.045101   
 ACH-001538             -0.715847        -0.748749        -0.045101   
 ACH-000242             -1.901403         0.094526        -0.045101   
 ...                          ...              ...              ...   
 TCGA-95-7947-01         2.007254         0.311515         0.479966   
 TCGA-VQ-AA6F-01         3.010084        -0.533079         0.049248   
 TCGA-BR-8588-01         0.466981        -0.560845        -0.112205   
 TCGA-24-2254-01        -0.372628        -0.508187        -0.006072   
 TCGA-DD-A115-01         0.710482         3.573195         0.000691   
 
                  ENSG00000186951  ENSG00000165496  ENSG00000158716  \
 ACH-001113              1.064159        -0.082715         0.599420   
 ACH-001289             -0.642396        -0.082715        -0.896522   
 ACH-001339              0.310372        -0.082715         1.062935   
 ACH-001538             -0.186993        -0.082715         1.277646   
 ACH-000242             -0.696503        -0.082715        -0.101637   
 ...                          ...              ...              ...   
 TCGA-95-7947-01         0.257332        -0.209169         2.257208   
 TCGA-VQ-AA6F-01         0.196070        -0.133590        -1.305097   
 TCGA-BR-8588-01         0.678235        -0.197266        -0.001516   
 TCGA-24-2254-01         0.383441        -0.046637         1.691917   
 TCGA-DD-A115-01         1.862516         3.667975         2.255484   
 
                  ENSG00000108417  ...  ENSG00000105088  ENSG00000136738  \
 ACH-001113             -0.029281  ...         2.249060        -0.560917   
 ACH-001289             -0.000712  ...         1.507593         0.735713   
 ACH-001339             -0.029281  ...        -0.331943         0.569889   
 ACH-001538             -0.029281  ...        -1.936014        -0.522519   
 ACH-000242             -0.029281  ...        -1.409945        -1.018368   
 ...                          ...  ...              ...              ...   
 TCGA-95-7947-01        -0.046484  ...        -1.577227        -0.543037   
 TCGA-VQ-AA6F-01        -0.076457  ...         0.200682        -0.863272   
 TCGA-BR-8588-01        -0.025777  ...        -2.000715        -0.525571   
 TCGA-24-2254-01        -0.025682  ...         1.359558        -0.432242   
 TCGA-DD-A115-01         0.052821  ...        -0.945550         0.092537   
 
                  ENSG00000142235  ENSG00000143952  ENSG00000161714  \
 ACH-001113             -0.632730         0.731039        -0.243562   
 ACH-001289              0.244527        -0.118298        -0.646753   
 ACH-001339             -1.128425         0.599954        -1.813311   
 ACH-001538             -0.346017         0.273617         1.272370   
 ACH-000242              0.015621        -0.366679         1.866808   
 ...                          ...              ...              ...   
 TCGA-95-7947-01         0.129522         0.071951        -1.136694   
 TCGA-VQ-AA6F-01         0.375005        -0.434374         1.684442   
 TCGA-BR-8588-01         0.346203        -0.505045         1.363059   
 TCGA-24-2254-01        -0.216573         0.075259         0.611565   
 TCGA-DD-A115-01        -0.309342        -0.354164         1.705096   
 
                  ENSG00000169800  ENSG00000148824  ENSG00000120705  \
 ACH-001113             -0.015512        -0.478588         1.223248   
 ACH-001289             -0.015512        -0.005185         0.752020   
 ACH-001339             -0.015512        -0.103483         0.227375   
 ACH-001538             -0.015512        -0.563289        -0.458711   
 ACH-000242             -0.015512         0.256358         0.334905   
 ...                          ...              ...              ...   
 TCGA-95-7947-01        -0.017232         0.993511         0.178246   
 TCGA-VQ-AA6F-01        -0.007522        -0.366667         0.357040   
 TCGA-BR-8588-01        -0.016503        -0.688111        -0.001788   
 TCGA-24-2254-01        -0.033650        -0.395078        -0.374550   
 TCGA-DD-A115-01         2.479497        -0.843512         0.149982   
 
                  ENSG00000112378  ENSG00000241322  
 ACH-001113              3.741698         2.614461  
 ACH-001289             -4.803032        -0.931972  
 ACH-001339              0.683418        -0.883473  
 ACH-001538              3.536902        -0.526212  
 ACH-000242              1.194860         0.180657  
 ...                          ...              ...  
 TCGA-95-7947-01         2.433189         1.174886  
 TCGA-VQ-AA6F-01         1.102051         0.656037  
 TCGA-BR-8588-01         1.435114        -0.625575  
 TCGA-24-2254-01        -0.236827         0.420977  
 TCGA-DD-A115-01        -0.393038         1.461601  
 
 [13647 rows x 18218 columns],
 [(401, 0),
  (796, 0),
  (1111, 0),
  (1087, 0),
  (443, 0),
  (7998, 1),
  (12308, 1),
  (12694, 1),
  (10821, 1),
  (6892, 1),
  (7791, 2),
  (1261, 2),
  (938, 2),
  (12315, 2),
  (2732, 3),
  (1176, 3),
  (1284, 3),
  (1039, 3),
  (494, 3),
  (2732, 4),
  (1284, 4),
  (494, 4),
  (9799, 4),
  (12970, 4),
  (5719, 5),
  (11349, 5),
  (245, 5),
  (3735, 5),
  (9736, 5),
  (8807, 6),
  (6492, 6),
  (11426, 6),
  (13357, 6),
  (13204, 6),
  (2371, 10),
  (2510, 10),
  (1984, 10),
  (6071, 10),
  (11100, 10),
  (2510, 11),
  (2079, 11),
  (2511, 11),
  (3051, 11),
  (2546, 12),
  (2781, 12),
  (1932, 12),
  (1858, 12),
  (1951, 12),
  (10028, 14),
  (1186, 15),
  (1091, 15),
  (868, 15),
  (1286, 15),
  (222, 15),
  (1186, 16),
  (868, 16),
  (1078, 16),
  (582, 16),
  (208, 16),
  (7791, 17),
  (86, 19),
  (1327, 19),
  (1142, 19),
  (921, 19),
  (587, 19),
  (11491, 21),
  (8605, 21),
  (10014, 22),
  (11491, 22),
  (9390, 22),
  (4287, 22),
  (8390, 22),
  (1087, 23),
  (1186, 23),
  (1315, 23),
  (221, 23),
  (582, 23),
  (1087, 24),
  (1186, 24),
  (1315, 24),
  (221, 24),
  (582, 24),
  (2717, 25),
  (1852, 25),
  (1430, 25),
  (2315, 25),
  (2134, 26),
  (2384, 26),
  (2521, 26),
  (2656, 26),
  (1611, 26),
  (1770, 27),
  (2371, 27),
  (6071, 27),
  (2510, 27),
  (1778, 27),
  (1770, 28),
  (6071, 28),
  (2510, 28),
  (2079, 28),
  (1778, 28),
  (10355, 29),
  (101, 30),
  (2872, 30),
  (808, 30),
  (262, 30),
  (13393, 30),
  (106, 31),
  (9583, 32),
  (4555, 32),
  (12709, 32),
  (4723, 32),
  (10810, 32),
  (1981, 33),
  (1091, 33),
  (1186, 33),
  (12679, 33),
  (102, 33),
  (1981, 34),
  (12679, 34),
  (10398, 34),
  (11554, 34),
  (5446, 34),
  (9156, 35),
  (9359, 35),
  (9158, 35),
  (6351, 36),
  (7697, 36),
  (11346, 36),
  (4096, 36),
  (10332, 36),
  (7697, 37),
  (6351, 37),
  (10332, 37),
  (11346, 37),
  (8701, 37),
  (4547, 38),
  (11492, 39),
  (6688, 39),
  (11161, 39),
  (7341, 39),
  (9824, 39),
  (10950, 40),
  (13502, 41),
  (10950, 41),
  (7603, 41),
  (12488, 41),
  (10282, 41),
  (3286, 42),
  (587, 42),
  (3164, 42),
  (735, 42),
  (7523, 42),
  (2714, 43),
  (2445, 43),
  (13289, 43),
  (2029, 43),
  (6594, 43),
  (4436, 44),
  (9249, 44),
  (11042, 44),
  (8605, 44),
  (4436, 45),
  (9249, 45),
  (11042, 45),
  (8605, 45),
  (2472, 46),
  (3116, 46),
  (2278, 46),
  (2182, 46),
  (2472, 47),
  (3116, 47),
  (4921, 48),
  (2048, 48),
  (4648, 48),
  (2713, 48),
  (2039, 48),
  (7401, 49),
  (11263, 49),
  (7934, 49),
  (6794, 49),
  (4104, 49),
  (7401, 50),
  (11263, 50),
  (4104, 50),
  (3305, 50),
  (11825, 50),
  (5599, 51),
  (8121, 51),
  (11985, 51),
  (13233, 51),
  (11606, 51),
  (5599, 52),
  (11985, 52),
  (8121, 52),
  (6888, 52),
  (13233, 52),
  (1556, 53),
  (8657, 53),
  (8544, 53),
  (12139, 53),
  (11235, 53),
  (1556, 54),
  (12901, 54),
  (8544, 54),
  (9089, 54),
  (7516, 55),
  (13111, 55),
  (7516, 56),
  (7805, 57),
  (4714, 57),
  (10217, 57),
  (11503, 57),
  (10288, 57),
  (7805, 58),
  (4714, 58),
  (4735, 58),
  (4635, 58),
  (6191, 59),
  (1034, 59),
  (7174, 59),
  (6372, 59),
  (10743, 59),
  (4430, 60),
  (9565, 60),
  (3703, 60),
  (8986, 60),
  (12431, 60),
  (31, 61),
  (4430, 61),
  (9565, 61),
  (10400, 61),
  (10157, 61),
  (6651, 62),
  (2403, 62),
  (987, 62),
  (1308, 62),
  (3784, 62),
  (2260, 63),
  (1645, 63),
  (10686, 63),
  (2473, 63),
  (2403, 63),
  (3789, 64),
  (12429, 64),
  (6317, 64),
  (8248, 64),
  (9220, 64),
  (8248, 65),
  (13482, 65),
  (5225, 65),
  (12429, 65),
  (3789, 65),
  (6826, 66),
  (7292, 66),
  (7061, 66),
  (3632, 66),
  (11569, 66),
  (7061, 67),
  (6016, 67),
  (10970, 67),
  (6826, 67),
  (7292, 67),
  (3305, 68),
  (6135, 69),
  (4147, 69),
  (5980, 69),
  (12050, 69),
  (8663, 69),
  (10379, 70),
  (5106, 70),
  (10379, 71),
  (531, 71),
  (1087, 72),
  (221, 72),
  (10199, 73),
  (8841, 73),
  (12679, 73),
  (11810, 73),
  (4829, 73),
  (10199, 74),
  (8841, 74),
  (11810, 74),
  (12679, 74),
  (3435, 74),
  (10504, 75),
  (3703, 75),
  (11041, 75),
  (3278, 75),
  (6917, 75),
  (7292, 76),
  (3278, 76),
  (10504, 76),
  (11041, 76),
  (6649, 76),
  (10355, 77),
  (869, 77),
  (5142, 77),
  (1123, 77),
  (10475, 77),
  (869, 78),
  (1123, 78),
  (813, 78),
  (10355, 78),
  (916, 78),
  (348, 79),
  (2781, 79),
  (201, 79),
  (2446, 79),
  (2860, 79),
  (763, 80),
  (2781, 80),
  (2860, 80),
  (699, 80),
  (201, 80),
  (3574, 81),
  (8754, 81),
  (8663, 81),
  (7073, 81),
  (12535, 81),
  (3574, 82),
  (8663, 82),
  (8754, 82),
  (7073, 82),
  (12900, 82),
  (7272, 83),
  (11505, 83),
  (5753, 83),
  (9083, 83),
  (342, 83),
  (7272, 84),
  (11505, 84),
  (5753, 84),
  (9083, 84),
  (342, 84),
  (10752, 85),
  (599, 85),
  (449, 86),
  (20, 86),
  (599, 86),
  (1131, 86),
  (4666, 87),
  (3724, 87),
  (8290, 87),
  (9586, 87),
  (12156, 87),
  (8290, 88),
  (7883, 88),
  (9586, 88),
  (4666, 88),
  (3724, 88),
  (7805, 89),
  (4714, 89),
  (8772, 89),
  (10217, 89),
  (10282, 89),
  (7805, 90),
  (4714, 90),
  (4635, 90),
  (4735, 90),
  (10282, 90),
  (10132, 91),
  (9221, 91),
  (8492, 91),
  (6755, 91),
  (9973, 91),
  (10132, 92),
  (8492, 92),
  (9278, 92),
  (9221, 92),
  (9428, 92),
  (8840, 93),
  (7802, 93),
  (11606, 93),
  (11385, 93),
  (8121, 93),
  (7802, 94),
  (11606, 94),
  (8840, 94),
  (11385, 94),
  (9248, 94),
  (9011, 95),
  (11745, 95),
  (8082, 95),
  (12332, 95),
  (8637, 95),
  (9011, 96),
  (8082, 96),
  (12332, 96),
  (6979, 96),
  (11745, 96),
  (8661, 97),
  (11392, 97),
  (11492, 97),
  (11135, 97),
  (9824, 97),
  (8661, 98),
  (11492, 98),
  (6085, 98),
  (9824, 98),
  (11392, 98),
  (10332, 99),
  (7238, 99),
  (4441, 99),
  (3786, 99),
  (8329, 99),
  (10332, 100),
  (7238, 100),
  (4441, 100),
  (8329, 100),
  (3786, 100),
  (7056, 101),
  (10096, 101),
  (9883, 101),
  (7863, 101),
  (10457, 101),
  (7056, 102),
  (10096, 102),
  (9883, 102),
  (7863, 102),
  (12335, 102),
  (3455, 103),
  (13356, 103),
  (3734, 103),
  (11407, 103),
  (10087, 103),
  (3455, 104),
  (13356, 104),
  (6955, 104),
  (13454, 104),
  (7415, 104),
  (6915, 105),
  (5719, 105),
  (3773, 105),
  (6987, 105),
  (5867, 105),
  (5719, 106),
  (6915, 106),
  (3773, 106),
  (5867, 106),
  (6987, 106),
  (449, 109),
  (504, 109),
  (450, 109),
  (528, 109),
  (530, 109),
  (1040, 110),
  (161, 110),
  (312, 110),
  (987, 110),
  (20, 110),
  (10296, 111),
  (1659, 111),
  (9762, 111),
  (10449, 111),
  (3034, 111),
  (10296, 112),
  (11154, 112),
  (1658, 112),
  (3034, 112),
  (326, 112),
  (575, 113),
  (906, 113),
  (1191, 113),
  (434, 113),
  (575, 114),
  (434, 114),
  (73, 114),
  (906, 114),
  (434, 115),
  (262, 115),
  (1191, 115),
  (26, 115),
  (664, 115),
  (5599, 116),
  (8840, 116),
  (5556, 116),
  (13163, 116),
  (4241, 116),
  (2799, 118),
  (2712, 118),
  (12901, 118),
  (9801, 118),
  (7803, 118),
  (2799, 119),
  (2714, 119),
  (2712, 119),
  (2445, 119),
  (12901, 119),
  (4141, 120),
  (2048, 120),
  (2527, 120),
  (3341, 120),
  (2035, 120),
  (4141, 121),
  (2048, 121),
  (3341, 121),
  (2527, 121),
  (3909, 121),
  (7401, 122),
  (5106, 122),
  (11263, 122),
  (814, 122),
  (3305, 122),
  (7401, 123),
  (5106, 123),
  (814, 123),
  (11263, 123),
  (10339, 123),
  (2771, 124),
  (6594, 124),
  (6071, 124),
  (2371, 124),
  (1540, 124),
  (2372, 125),
  (2207, 125),
  (3091, 125),
  (2725, 125),
  (2372, 126),
  (2207, 126),
  (3091, 126),
  (7196, 126),
  (2725, 126),
  (1087, 127),
  (1315, 127),
  (221, 127),
  (423, 128),
  (936, 128),
  (308, 128),
  (7845, 128),
  (5189, 128),
  (423, 129),
  (936, 129),
  (7845, 129),
  (5189, 129),
  (6882, 129),
  (3989, 130),
  (6814, 130),
  (8683, 130),
  (9927, 130),
  (6748, 130),
  (808, 131),
  (1182, 131),
  (2402, 131),
  (1907, 131),
  (231, 131),
  (808, 132),
  (1182, 132),
  (2402, 132),
  (666, 132),
  (1907, 132),
  (11759, 133),
  (6748, 133),
  (11027, 133),
  (9011, 133),
  (11823, 133),
  (11759, 134),
  (6748, 134),
  (11027, 134),
  (9011, 134),
  (11823, 134),
  (7910, 135),
  (7511, 138),
  (10218, 138),
  (8118, 138),
  (6436, 138),
  (7106, 138),
  (10218, 139),
  (7511, 139),
  (7438, 139),
  (8163, 139),
  (11419, 139),
  (6491, 140),
  (8415, 140),
  (4905, 140),
  (7679, 140),
  (5377, 140),
  (6491, 141),
  (5377, 141),
  (8415, 141),
  (4905, 141),
  (1281, 141),
  (9561, 142),
  (4990, 142),
  (12651, 142),
  (512, 142),
  (12585, 142),
  (4990, 143),
  (9561, 143),
  (4381, 143),
  (12651, 143),
  (12585, 143),
  (1048, 144),
  (3784, 144),
  (4875, 144),
  (8425, 144),
  (2029, 144),
  (3106, 145),
  (3784, 145),
  (2029, 145),
  (4875, 145),
  (8425, 145),
  (5195, 146),
  (3835, 146),
  (9697, 146),
  (12865, 146),
  (9605, 146),
  (5195, 147),
  (11160, 147),
  (1924, 147),
  (961, 147),
  (916, 147),
  (8242, 149),
  (1723, 149),
  (6873, 149),
  (4576, 150),
  (12283, 150),
  (21, 150),
  (6895, 150),
  (4556, 150),
  (6895, 151),
  (11298, 151),
  (21, 151),
  (1322, 151),
  (12894, 151),
  (6253, 152),
  (8026, 152),
  (7364, 152),
  (12041, 152),
  (6364, 152),
  (1142, 153),
  (2781, 153),
  (1039, 153),
  (2120, 153),
  (2860, 153),
  (1039, 154),
  (2120, 154),
  (2781, 154),
  (1457, 154),
  (2760, 154),
  (4444, 155),
  (8679, 155),
  (12309, 155),
  (10769, 155),
  (9334, 155),
  (4444, 156),
  (10769, 156),
  (11363, 156),
  (7364, 156),
  (9334, 156),
  (1186, 157),
  (1087, 157),
  (208, 157),
  (582, 157),
  (222, 157),
  (1382, 158),
  (11606, 158),
  (11385, 158),
  (5599, 158),
  (5925, 158),
  (1382, 159),
  (11385, 159),
  (5599, 159),
  (5925, 159),
  (9948, 159),
  (7401, 160),
  (5106, 160),
  (11263, 160),
  (11825, 160),
  (6930, 160),
  (7401, 161),
  (5106, 161),
  (11263, 161),
  (6930, 161),
  (11825, 161),
  (10339, 162),
  (8544, 162),
  (5161, 162),
  (8657, 162),
  (13567, 162),
  (10339, 163),
  (8544, 163),
  (10493, 163),
  (9152, 163),
  (9089, 163),
  (6585, 164),
  (12901, 164),
  (9801, 164),
  (12901, 165),
  (6585, 165),
  (1300, 165),
  (9801, 165),
  (7645, 165),
  (11477, 166),
  (3889, 166),
  (13407, 166),
  (6561, 166),
  (6086, 166),
  (11477, 167),
  (3889, 167),
  (13407, 167),
  (6086, 167),
  (6561, 167),
  (13239, 168),
  (4850, 168),
  (3781, 168),
  (10579, 168),
  (12439, 168),
  (704, 169),
  (704, 170),
  (11693, 171),
  (13088, 171),
  (12734, 171),
  (3988, 171),
  (195, 171),
  (11693, 172),
  (13088, 172),
  (195, 172),
  (3988, 172),
  (5416, 172),
  (7034, 173),
  (9488, 173),
  (3296, 173),
  (5223, 173),
  (4696, 173),
  (13424, 174),
  (6691, 174),
  (8657, 175),
  (11263, 175),
  (4268, 175),
  (3305, 175),
  (11235, 175),
  (7384, 176),
  (3472, 177),
  (10101, 177),
  (7863, 177),
  (5637, 177),
  (9883, 177),
  (4973, 178),
  (3472, 178),
  (10101, 178),
  (4950, 178),
  (9883, 178),
  (12029, 179),
  (2528, 179),
  (2740, 179),
  (2456, 179),
  (2199, 179),
  (1832, 180),
  (1540, 180),
  (2771, 180),
  (2265, 180),
  (9362, 180),
  (1832, 181),
  (2771, 181),
  (1540, 181),
  (12153, 181),
  (2265, 181),
  (4215, 182),
  (13413, 182),
  (7634, 182),
  (9720, 182),
  (4215, 183),
  (9720, 183),
  (13413, 183),
  (7634, 183),
  (8131, 184),
  (1536, 184),
  (2309, 184),
  (4134, 184),
  (12523, 184),
  (1536, 185),
  (8131, 185),
  (7830, 185),
  (12523, 185),
  (7557, 185),
  (599, 186),
  (1003, 186),
  (1149, 186),
  (2930, 186),
  (6135, 187),
  (8663, 187),
  (11582, 187),
  (10939, 187),
  (9891, 187),
  (6135, 188),
  (8663, 188),
  (10939, 188),
  (11582, 188),
  (9891, 188),
  (1679, 189),
  (3472, 189),
  (871, 189),
  (10900, 189),
  (4973, 189),
  (1679, 190),
  (3472, 190),
  (10900, 190),
  (871, 190),
  (8361, 190),
  (5232, 191),
  (6558, 191),
  (6430, 191),
  (7112, 191),
  (4332, 191),
  (5232, 192),
  (6558, 192),
  (6430, 192),
  (7112, 192),
  (4332, 192),
  (9883, 193),
  (7056, 193),
  (11640, 193),
  (10457, 193),
  (10096, 193),
  (9883, 194),
  (7056, 194),
  (11640, 194),
  (10096, 194),
  (10457, 194),
  (857, 195),
  (626, 195),
  (2493, 195),
  (1013, 195),
  (10014, 196),
  (626, 196),
  (2493, 196),
  (11491, 196),
  (5182, 196),
  (12471, 197),
  (5586, 197),
  (2029, 197),
  (2631, 197),
  (6341, 197),
  (12471, 198),
  (2029, 198),
  (5586, 198),
  (2631, 198),
  (6341, 198),
  (2074, 199),
  (1877, 199),
  (11263, 200),
  (3305, 200),
  (7401, 200),
  (11825, 200),
  (8657, 200),
  (11263, 201),
  (11825, 201),
  (6930, 201),
  (8657, 201),
  (3305, 201),
  (5106, 202),
  (3750, 202),
  (3750, 203),
  (5106, 203),
  (7913, 203),
  (7805, 204),
  (10217, 204),
  (6975, 204),
  (7498, 204),
  (4714, 204),
  (7805, 205),
  (10217, 205),
  (4714, 205),
  (10945, 205),
  (2029, 206),
  (2027, 206),
  (9509, 206),
  (10503, 206),
  (2583, 206),
  (2029, 207),
  (9509, 207),
  (2027, 207),
  (10503, 207),
  (2583, 207),
  (7246, 208),
  (5587, 208),
  (6451, 208),
  (6777, 208),
  (4274, 208),
  (5587, 209),
  (7246, 209),
  (6451, 209),
  (12111, 209),
  (4274, 209),
  (5636, 210),
  (8661, 210),
  (5420, 210),
  (1386, 210),
  (13444, 210),
  (5636, 211),
  (5420, 211),
  (8661, 211),
  (21, 211),
  (13444, 211),
  (12901, 212),
  (6585, 212),
  (9801, 212),
  (8657, 212),
  (12901, 213),
  (6585, 213),
  (9801, 213),
  (11806, 214),
  (11806, 215),
  (8821, 215),
  (5925, 216),
  (5599, 216),
  (6162, 216),
  (13626, 216),
  (6005, 216),
  (7401, 217),
  (5106, 217),
  (7401, 218),
  (5106, 218),
  (814, 218),
  (5174, 219),
  (7230, 219),
  (10321, 219),
  (12228, 219),
  (9817, 219),
  (2029, 220),
  (2027, 220),
  (1696, 220),
  (1308, 220),
  (5494, 220),
  (10729, 221),
  (7682, 221),
  (1208, 221),
  (12851, 221),
  (4629, 221),
  (1087, 222),
  (221, 222),
  (1315, 222),
  (1332, 222),
  (582, 222),
  (8783, 223),
  (6872, 223),
  (7278, 223),
  (3888, 223),
  (6332, 223),
  (1186, 224),
  (1087, 224),
  (582, 224),
  (208, 224),
  (222, 224),
  (12806, 225),
  (9563, 225),
  (10743, 225),
  (7865, 225),
  (7174, 225),
  (1858, 226),
  (1951, 226),
  (7573, 226),
  (3087, 226),
  (1618, 226),
  (3630, 227),
  (6664, 227),
  (8244, 227),
  (13135, 227),
  (12704, 227),
  (8244, 228),
  (12704, 228),
  (3630, 228),
  (6664, 228),
  (13135, 228),
  (7401, 229),
  (5106, 229),
  (11263, 229),
  (6930, 229),
  (7852, 229),
  (7401, 230),
  (5106, 230),
  (11263, 230),
  (6930, 230),
  (7852, 230),
  (8044, 231),
  (6888, 231),
  (10827, 231),
  (1382, 231),
  (10425, 231),
  (8044, 232),
  (1382, 232),
  (5599, 232),
  (6888, 232),
  (10827, 232),
  (8618, 233),
  (687, 233),
  (13395, 233),
  (18, 233),
  (4204, 233),
  (4585, 234),
  (4898, 234),
  (5473, 234),
  (13444, 234),
  (7034, 234),
  (4585, 235),
  (5473, 235),
  (4898, 235),
  (7034, 235),
  (13444, 235),
  ...])
In [54]:
Novartis_PDX_TPM = Novartis_PDX_TPM.loc[:,set(Novartis_PDX_TPM)& set(pediatric_PDX_TPM)]
pediatric_PDX_TPM = pediatric_PDX_TPM.loc[:,set(Novartis_PDX_TPM)& set(pediatric_PDX_TPM)]
In [58]:
pediatric_PDX_ann['cell_type'] = "PDX_2"
In [64]:
Novartis_PDX_ann = Novartis_PDX_ann.loc[Novartis_PDX_TPM.index]
pediatric_PDX_ann = pediatric_PDX_ann.loc[pediatric_PDX_TPM.index]
In [55]:
my_alligner.putAllToFit(redo_diff=False)
clustering...
WARNING: You’re trying to run this on 18218 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
done
In [74]:
_= my_alligner.transform(pd.concat([Novartis_PDX_TPM, pediatric_PDX_TPM]), pd.concat([Novartis_PDX_ann, pediatric_PDX_ann]), recompute_contamination=False)
looking at 689 samples.
found 18049 common genes
creating a transform input..
clustering..
WARNING: You’re trying to run this on 18049 dimensions of `.X`, if you really want this, set `use_rep='X'`.
         Falling back to preprocessing with `sc.pp.pca` and default params.
reducing dimensionality...
doing differential expression analysis on the clusters..
running differential expression on 22 clusters
running limmapy on the samples
you need to have R installed with the limma library installed
3.4.5
there is 0.208 overlap between the fit and transform dataset in their most variable genes
regressing out the cPCA components..
doing the MNN analysis using Marioni et al. method..
Performing cosine normalization...
  Looking for MNNs...
  Found 3023 mutual nearest neighbors.
done
reducing dimensionality...
making plot...
Out[74]:
(           ENSG00000229665  ENSG00000139970  ENSG00000181754  ENSG00000185507  \
 0931HXXTM         0.001477        -0.944954        -0.293398         0.237567   
 0933HXXTM         0.019329        -0.910039         0.076859         1.045271   
 0991HXXTM        -0.002687        -1.183752        -0.711505        -0.449807   
 1004HXXTM        -0.000616        -0.983647         1.305305        -1.429069   
 1008HXXTM         0.025634        -1.498710        -0.261573        -1.292214   
 ...                    ...              ...              ...              ...   
 PALKTY           -0.017439        -1.139948        -0.434517         1.175101   
 PALLSD           -0.017440        -1.145475        -0.681486         1.535483   
 PALNTB           -0.016739        -1.118368        -0.478267         0.588895   
 PALTWS           -0.010727        -1.085191        -0.539035         0.529335   
 PAMDRM           -0.018217        -1.126442        -0.362001         0.690101   
 
            ENSG00000151790  ENSG00000244623  ENSG00000186951  ENSG00000165496  \
 0931HXXTM         0.139724         0.254102         0.363062        -0.191407   
 0933HXXTM         0.856340        -0.022219         0.036528        -1.415633   
 0991HXXTM        -0.222492        -0.049437        -0.286520        -0.332777   
 1004HXXTM         0.085351        -0.366008        -0.274358        -0.187573   
 1008HXXTM        -0.901574        -0.034186         0.539295        -0.271945   
 ...                    ...              ...              ...              ...   
 PALKTY           -0.470680        -0.067329         1.300755        -0.068188   
 PALLSD           -0.422616        -0.041373         0.274305        -0.068094   
 PALNTB           -0.479191        -0.077234         1.210914        -0.065618   
 PALTWS           -0.391353        -0.065141         0.574779        -0.068980   
 PAMDRM           -0.458415        -0.097897         0.505233        -0.063031   
 
            ENSG00000158716  ENSG00000108417  ...  ENSG00000105088  \
 0931HXXTM         0.533365         0.061846  ...        -0.536319   
 0933HXXTM         2.647427         0.343943  ...        -1.453991   
 0991HXXTM         0.301258         0.126405  ...        -0.814847   
 1004HXXTM         1.748886         0.013144  ...         0.446403   
 1008HXXTM         1.801359         0.030352  ...         1.414260   
 ...                    ...              ...  ...              ...   
 PALKTY           -2.404297        -0.191192  ...        -1.709095   
 PALLSD           -1.669545        -0.192015  ...        -1.584042   
 PALNTB           -3.492029        -0.195391  ...        -1.286339   
 PALTWS           -2.783169        -0.159536  ...        -1.488557   
 PAMDRM           -2.302024        -0.200427  ...        -1.397392   
 
            ENSG00000136738  ENSG00000142235  ENSG00000143952  ENSG00000161714  \
 0931HXXTM        -0.462695         0.349170        -0.275609        -1.423587   
 0933HXXTM        -0.760831         0.783691         0.034080         1.336372   
 0991HXXTM         0.083196         0.791554        -0.073352         0.536835   
 1004HXXTM         0.092326         1.328493         0.705973        -1.007834   
 1008HXXTM         0.689251        -0.603206         0.047620        -0.759529   
 ...                    ...              ...              ...              ...   
 PALKTY           -0.924709        -0.286945         0.019260        -2.279944   
 PALLSD           -0.964274        -0.391503         0.378273        -3.032498   
 PALNTB           -0.925151        -0.380556         0.426970        -2.761724   
 PALTWS           -0.594624        -0.330008         0.143609        -2.242012   
 PAMDRM           -0.315870        -0.318361         0.337049        -3.483328   
 
            ENSG00000169800  ENSG00000148824  ENSG00000120705  ENSG00000112378  \
 0931HXXTM        -0.007545        -1.036299         0.420176         3.827706   
 0933HXXTM         0.007040        -0.214194         0.280332         3.655299   
 0991HXXTM        -0.014260        -0.282392         0.104538         2.791547   
 1004HXXTM         0.007448         0.691886         0.086273         1.585746   
 1008HXXTM        -0.017524        -1.444551         0.236676         2.774803   
 ...                    ...              ...              ...              ...   
 PALKTY            0.011896         0.673275         0.385812        -2.932765   
 PALLSD            0.014440         0.709622         0.412164        -2.843692   
 PALNTB            0.012995         0.590584         0.144982        -2.869281   
 PALTWS            0.014364         0.162649         0.231590        -2.890001   
 PAMDRM            0.012195         0.529683         0.133408        -2.856611   
 
            ENSG00000241322  
 0931HXXTM         1.153125  
 0933HXXTM         0.350684  
 0991HXXTM         1.687881  
 1004HXXTM         0.502254  
 1008HXXTM         1.040609  
 ...                    ...  
 PALKTY           -0.866999  
 PALLSD           -0.851324  
 PALNTB           -1.019294  
 PALTWS           -0.986884  
 PAMDRM           -1.037405  
 
 [689 rows x 18049 columns],
                                  ENSG00000229665  ENSG00000139970  \
 ACH-001113                             -0.012122         0.695668   
 ACH-001289                             -0.012122         3.368767   
 ACH-001339                              0.002233        -0.996209   
 ACH-001538                             -0.012122        -1.024224   
 ACH-000242                             -0.012122        -1.024224   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         0.003279         2.097418   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.011900        -0.973947   
 TP_2131-capt-SI_11906-C7F4VANXX         0.000935        -0.571228   
 TP_2141-capt-SI_12056-H53C5ADXX         0.041927        -1.088706   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.002092         4.204988   
 
                                  ENSG00000181754  ENSG00000185507  \
 ACH-001113                              0.914510        -0.160200   
 ACH-001289                              1.480198        -2.859583   
 ACH-001339                             -0.405730         0.880471   
 ACH-001538                              0.300539        -0.715847   
 ACH-000242                             -0.284424        -1.901403   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         0.909413         0.234904   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.241607         0.305689   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.126598         0.354367   
 TP_2141-capt-SI_12056-H53C5ADXX         0.415384        -0.025494   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.631829        -1.295765   
 
                                  ENSG00000151790  ENSG00000244623  \
 ACH-001113                             -0.652990         0.205861   
 ACH-001289                             -0.748749        -0.045101   
 ACH-001339                              0.927554        -0.045101   
 ACH-001538                             -0.748749        -0.045101   
 ACH-000242                              0.094526        -0.045101   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         1.541525         0.167493   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.728589         0.011243   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.202375         0.057435   
 TP_2141-capt-SI_12056-H53C5ADXX         0.714452        -0.079891   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.241180         0.072492   
 
                                  ENSG00000186951  ENSG00000165496  \
 ACH-001113                              1.064159        -0.082715   
 ACH-001289                             -0.642396        -0.082715   
 ACH-001339                              0.310372        -0.082715   
 ACH-001538                             -0.186993        -0.082715   
 ACH-000242                             -0.696503        -0.082715   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -0.196875         0.392018   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.566015        -0.079536   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.305369        -0.094815   
 TP_2141-capt-SI_12056-H53C5ADXX         0.046453        -0.308889   
 TP_2156-capt-SI_12477-C7G91ANXX         0.228639         0.007876   
 
                                  ENSG00000158716  ENSG00000108417  ...  \
 ACH-001113                              0.599420        -0.029281  ...   
 ACH-001289                             -0.896522        -0.000712  ...   
 ACH-001339                              1.062935        -0.029281  ...   
 ACH-001538                              1.277646        -0.029281  ...   
 ACH-000242                             -0.101637        -0.029281  ...   
 ...                                          ...              ...  ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -1.474862        -0.164041  ...   
 TP_2130-capt-SI_11905-C7FMDANXX         1.151907         0.222681  ...   
 TP_2131-capt-SI_11906-C7F4VANXX         1.080469         0.055891  ...   
 TP_2141-capt-SI_12056-H53C5ADXX         1.768405        -0.269647  ...   
 TP_2156-capt-SI_12477-C7G91ANXX         2.362499        -0.772788  ...   
 
                                  ENSG00000105088  ENSG00000136738  \
 ACH-001113                              2.249060        -0.560917   
 ACH-001289                              1.507593         0.735713   
 ACH-001339                             -0.331943         0.569889   
 ACH-001538                             -1.936014        -0.522519   
 ACH-000242                             -1.409945        -1.018368   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -1.772989        -0.445764   
 TP_2130-capt-SI_11905-C7FMDANXX        -1.517982         0.534567   
 TP_2131-capt-SI_11906-C7F4VANXX        -2.190997        -0.170856   
 TP_2141-capt-SI_12056-H53C5ADXX         1.776177         0.068475   
 TP_2156-capt-SI_12477-C7G91ANXX        -1.326375        -0.822000   
 
                                  ENSG00000142235  ENSG00000143952  \
 ACH-001113                             -0.632730         0.731039   
 ACH-001289                              0.244527        -0.118298   
 ACH-001339                             -1.128425         0.599954   
 ACH-001538                             -0.346017         0.273617   
 ACH-000242                              0.015621        -0.366679   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX        -1.177888        -0.214526   
 TP_2130-capt-SI_11905-C7FMDANXX         0.012539        -0.174808   
 TP_2131-capt-SI_11906-C7F4VANXX         0.018638         0.058551   
 TP_2141-capt-SI_12056-H53C5ADXX        -0.022322        -0.676249   
 TP_2156-capt-SI_12477-C7G91ANXX        -0.495633         1.077309   
 
                                  ENSG00000161714  ENSG00000169800  \
 ACH-001113                             -0.243562        -0.015512   
 ACH-001289                             -0.646753        -0.015512   
 ACH-001339                             -1.813311        -0.015512   
 ACH-001538                              1.272370        -0.015512   
 ACH-000242                              1.866808        -0.015512   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         2.088491        -0.013928   
 TP_2130-capt-SI_11905-C7FMDANXX         2.029802        -0.034686   
 TP_2131-capt-SI_11906-C7F4VANXX         0.398697        -0.035416   
 TP_2141-capt-SI_12056-H53C5ADXX        -0.039405        -0.024161   
 TP_2156-capt-SI_12477-C7G91ANXX        -4.125488        -0.019349   
 
                                  ENSG00000148824  ENSG00000120705  \
 ACH-001113                             -0.478588         1.223248   
 ACH-001289                             -0.005185         0.752020   
 ACH-001339                             -0.103483         0.227375   
 ACH-001538                             -0.563289        -0.458711   
 ACH-000242                              0.256358         0.334905   
 ...                                          ...              ...   
 TP_2123-poly-SI_11689-C7G60ANXX         0.267123         0.183217   
 TP_2130-capt-SI_11905-C7FMDANXX        -0.563423         0.117468   
 TP_2131-capt-SI_11906-C7F4VANXX        -0.318430         0.060895   
 TP_2141-capt-SI_12056-H53C5ADXX        -0.025030         0.446102   
 TP_2156-capt-SI_12477-C7G91ANXX         0.246973        -0.563621   
 
                                  ENSG00000112378  ENSG00000241322  
 ACH-001113                              3.741698         2.614461  
 ACH-001289                             -4.803032        -0.931972  
 ACH-001339                              0.683418        -0.883473  
 ACH-001538                              3.536902        -0.526212  
 ACH-000242                              1.194860         0.180657  
 ...                                          ...              ...  
 TP_2123-poly-SI_11689-C7G60ANXX        -0.438502         0.549056  
 TP_2130-capt-SI_11905-C7FMDANXX         2.071235         1.564062  
 TP_2131-capt-SI_11906-C7F4VANXX         3.676588         2.140582  
 TP_2141-capt-SI_12056-H53C5ADXX         1.383039         0.402192  
 TP_2156-capt-SI_12477-C7G91ANXX         1.935112        -0.856332  
 
 [14515 rows x 18049 columns],
 [(1275, 0),
  (520, 0),
  (1263, 0),
  (4778, 0),
  (3542, 0),
  (1224, 1),
  (107, 1),
  (245, 1),
  (364, 1),
  (12879, 1),
  (78, 2),
  (520, 2),
  (7174, 2),
  (459, 3),
  (607, 3),
  (336, 3),
  (401, 3),
  (9623, 3),
  (7108, 4),
  (3605, 4),
  (9623, 4),
  (336, 4),
  (10132, 4),
  (1233, 5),
  (7834, 5),
  (5, 5),
  (5283, 5),
  (474, 6),
  (1224, 6),
  (107, 6),
  (245, 6),
  (372, 6),
  (1224, 7),
  (6850, 7),
  (107, 7),
  (14181, 7),
  (4288, 7),
  (3121, 8),
  (6850, 9),
  (12340, 9),
  (6171, 9),
  (107, 9),
  (4288, 9),
  (1275, 10),
  (9023, 10),
  (7228, 10),
  (4778, 10),
  (13223, 10),
  (6148, 11),
  (1079, 11),
  (9951, 11),
  (3655, 11),
  (7852, 11),
  (1224, 12),
  (107, 12),
  (245, 12),
  (12879, 12),
  (7834, 12),
  (8625, 13),
  (3630, 13),
  (10579, 13),
  (8682, 14),
  (5, 15),
  (1224, 15),
  (364, 15),
  (5719, 15),
  (10699, 15),
  (107, 16),
  (1224, 16),
  (12879, 16),
  (4288, 16),
  (603, 16),
  (107, 17),
  (245, 17),
  (803, 17),
  (9063, 17),
  (13239, 18),
  (13815, 18),
  (10579, 18),
  (8625, 18),
  (4987, 18),
  (364, 19),
  (137, 19),
  (245, 19),
  (955, 19),
  (74, 20),
  (53, 20),
  (531, 20),
  (607, 20),
  (3301, 20),
  (1224, 21),
  (245, 21),
  (364, 21),
  (137, 21),
  (13652, 21),
  (14187, 23),
  (4296, 23),
  (113, 23),
  (477, 23),
  (10554, 23),
  (390, 24),
  (1031, 25),
  (100, 25),
  (1136, 25),
  (7827, 25),
  (10561, 26),
  (11486, 26),
  (1303, 26),
  (11540, 26),
  (5403, 26),
  (401, 27),
  (607, 27),
  (531, 27),
  (53, 27),
  (74, 27),
  (225, 28),
  (13779, 28),
  (14353, 28),
  (13920, 28),
  (1077, 28),
  (520, 29),
  (1275, 29),
  (1263, 29),
  (669, 29),
  (7609, 29),
  (520, 30),
  (1275, 30),
  (1263, 30),
  (221, 30),
  (170, 30),
  (459, 31),
  (14232, 31),
  (13737, 31),
  (8220, 31),
  (1342, 32),
  (103, 32),
  (5721, 32),
  (13735, 32),
  (9623, 34),
  (8220, 34),
  (14232, 34),
  (336, 34),
  (10877, 34),
  (3701, 35),
  (7683, 35),
  (13706, 35),
  (5066, 35),
  (1224, 36),
  (245, 36),
  (107, 36),
  (9850, 36),
  (7834, 36),
  (814, 37),
  (9956, 37),
  (5106, 37),
  (245, 38),
  (5, 38),
  (6915, 38),
  (5719, 38),
  (6987, 38),
  (13886, 39),
  (1770, 39),
  (14173, 39),
  (1778, 39),
  (13657, 39),
  (1087, 40),
  (221, 40),
  (459, 40),
  (1315, 40),
  (12676, 41),
  (11117, 41),
  (10561, 41),
  (13638, 41),
  (5721, 41),
  (364, 42),
  (955, 42),
  (137, 42),
  (245, 42),
  (747, 42),
  (12879, 43),
  (419, 43),
  (1224, 43),
  (245, 43),
  (107, 43),
  (650, 44),
  (3394, 44),
  (3886, 44),
  (9212, 44),
  (12876, 44),
  (245, 45),
  (1224, 45),
  (5719, 45),
  (747, 45),
  (506, 46),
  (1350, 46),
  (467, 46),
  (588, 46),
  (1224, 47),
  (245, 47),
  (372, 47),
  (107, 47),
  (12879, 47),
  (1224, 48),
  (245, 48),
  (137, 48),
  (419, 48),
  (107, 49),
  (6850, 49),
  (5283, 49),
  (4288, 49),
  (12879, 49),
  (975, 50),
  (9644, 50),
  (13871, 50),
  (11871, 50),
  (1342, 51),
  (9096, 51),
  (1303, 51),
  (103, 51),
  (11461, 51),
  (1087, 52),
  (520, 52),
  (221, 52),
  (257, 52),
  (14400, 53),
  (2529, 53),
  (499, 53),
  (6964, 53),
  (1913, 53),
  (520, 54),
  (1275, 54),
  (257, 54),
  (1263, 54),
  (552, 54),
  (6191, 55),
  (10743, 55),
  (13706, 55),
  (7865, 55),
  (3957, 55),
  (9938, 56),
  (5109, 56),
  (3147, 56),
  (5100, 56),
  (13149, 56),
  (520, 57),
  (1275, 57),
  (1263, 57),
  (257, 57),
  (275, 57),
  (1342, 58),
  (103, 58),
  (1303, 58),
  (13735, 58),
  (12635, 58),
  (650, 60),
  (14178, 60),
  (1146, 60),
  (3886, 60),
  (11880, 60),
  (172, 61),
  (221, 61),
  (520, 61),
  (1315, 61),
  (1275, 61),
  (1063, 62),
  (12545, 62),
  (814, 62),
  (1079, 62),
  (7557, 62),
  (1275, 63),
  (11299, 63),
  (4060, 63),
  (13124, 63),
  (328, 63),
  (459, 64),
  (1087, 64),
  (401, 64),
  (1111, 64),
  (531, 64),
  (1062, 65),
  (14269, 65),
  (9332, 65),
  (14270, 65),
  (6764, 65),
  (6181, 66),
  (6561, 66),
  (11477, 66),
  (6587, 66),
  (12626, 66),
  (8124, 67),
  (9054, 67),
  (512, 67),
  (1120, 67),
  (267, 69),
  (199, 69),
  (257, 69),
  (1913, 70),
  (14400, 70),
  (2060, 70),
  (6187, 71),
  (6947, 71),
  (4939, 71),
  (10393, 71),
  (6301, 71),
  (11477, 72),
  (13270, 72),
  (13407, 72),
  (13056, 72),
  (3889, 72),
  (1224, 73),
  (803, 73),
  (107, 73),
  (7834, 73),
  (245, 73),
  (3516, 74),
  (11880, 74),
  (3886, 74),
  (6947, 74),
  (6183, 74),
  (245, 75),
  (5, 75),
  (355, 75),
  (364, 75),
  (13825, 76),
  (10688, 76),
  (10435, 76),
  (1201, 76),
  (7920, 76),
  (459, 77),
  (336, 77),
  (9623, 77),
  (14232, 78),
  (13737, 78),
  (11754, 79),
  (11052, 79),
  (702, 79),
  (12645, 79),
  (1087, 82),
  (14230, 83),
  (8940, 83),
  (14231, 83),
  (517, 84),
  (602, 84),
  (172, 84),
  (13708, 84),
  (6183, 84),
  (14140, 85),
  (5839, 85),
  (5033, 85),
  (1116, 85),
  (9790, 85),
  (650, 86),
  (199, 86),
  (520, 86),
  (517, 86),
  (3394, 86),
  (1224, 87),
  (107, 87),
  (6850, 87),
  (13706, 87),
  (13815, 87),
  (13815, 88),
  (12340, 88),
  (3836, 88),
  (3630, 88),
  (8625, 88),
  (533, 89),
  (4239, 89),
  (1275, 90),
  (5653, 90),
  (10896, 90),
  (3273, 90),
  (8416, 90),
  (252, 91),
  (13815, 92),
  (7248, 92),
  (12492, 92),
  (6191, 92),
  (13239, 92),
  (13239, 93),
  (4987, 93),
  (7128, 93),
  (12492, 93),
  (6850, 93),
  (13901, 94),
  (11477, 94),
  (13932, 94),
  (5049, 94),
  (1031, 94),
  (257, 95),
  (1087, 95),
  (221, 95),
  (390, 95),
  (5839, 96),
  (14140, 96),
  (1275, 96),
  (520, 96),
  (5033, 96),
  (11880, 97),
  (4939, 97),
  (7218, 97),
  (5653, 97),
  (6622, 97),
  (11880, 98),
  (9241, 98),
  (3886, 98),
  (6947, 98),
  (11969, 98),
  (459, 99),
  (1275, 100),
  (11299, 100),
  (3604, 100),
  (12949, 100),
  (4092, 100),
  (107, 101),
  (6850, 101),
  (4874, 101),
  (12287, 101),
  (531, 102),
  (13825, 103),
  (7995, 103),
  (9938, 103),
  (11342, 103),
  (10435, 103),
  (5, 104),
  (1233, 104),
  (364, 104),
  (74, 105),
  (531, 105),
  (607, 105),
  (147, 105),
  (836, 105),
  (13239, 106),
  (10579, 106),
  (3957, 106),
  (3701, 106),
  (3630, 106),
  (13815, 107),
  (107, 107),
  (13743, 107),
  (6171, 107),
  (6850, 107),
  (1342, 108),
  (103, 108),
  (13735, 108),
  (1303, 108),
  (3644, 108),
  (13930, 109),
  (14400, 109),
  (13929, 109),
  (1913, 109),
  (2643, 109),
  (13815, 110),
  (10579, 110),
  (7683, 110),
  (1275, 111),
  (520, 111),
  (1263, 111),
  (4778, 111),
  (6979, 111),
  (5, 112),
  (257, 113),
  (390, 113),
  (13834, 113),
  (1970, 114),
  (3212, 114),
  (2411, 114),
  (2866, 114),
  (2012, 114),
  (13815, 115),
  (10579, 115),
  (13239, 115),
  (10743, 115),
  (4850, 115),
  (13737, 116),
  (4338, 116),
  (1087, 117),
  (227, 117),
  (13825, 117),
  (6008, 117),
  (1399, 117),
  (1275, 118),
  (11299, 118),
  (13751, 118),
  (13750, 118),
  (3604, 118),
  (13815, 119),
  (12492, 119),
  (10579, 119),
  (7248, 119),
  (7174, 119),
  (459, 120),
  (1342, 121),
  (103, 121),
  (1303, 121),
  (4635, 122),
  (10805, 122),
  (1224, 124),
  (245, 124),
  (142, 124),
  (14232, 125),
  (107, 126),
  (7834, 126),
  (567, 126),
  (1224, 126),
  (419, 126),
  (3957, 127),
  (7248, 127),
  (13239, 127),
  (4987, 127),
  (12492, 127),
  (7174, 128),
  (6191, 128),
  (7248, 128),
  (10973, 128),
  (7099, 128),
  (14400, 130),
  (1913, 130),
  (2643, 130),
  (499, 130),
  (1149, 130),
  (173, 131),
  (11957, 132),
  (7683, 132),
  (3701, 132),
  (8683, 132),
  (5990, 132),
  (7174, 133),
  (6191, 133),
  (10973, 133),
  (7099, 133),
  (12564, 133),
  (5851, 134),
  (13834, 134),
  (285, 134),
  (9960, 134),
  (6171, 135),
  (107, 135),
  (13629, 135),
  (6850, 135),
  (1224, 135),
  (245, 136),
  (355, 136),
  (1224, 136),
  (5719, 136),
  (7059, 136),
  (10071, 137),
  (13737, 137),
  (8220, 137),
  (7108, 137),
  (12692, 137),
  (270, 138),
  (13930, 138),
  (139, 138),
  (13929, 138),
  (1913, 138),
  (245, 139),
  (1224, 139),
  (355, 139),
  (364, 139),
  (142, 139),
  (459, 141),
  (172, 142),
  (1275, 142),
  (648, 142),
  (888, 142),
  (520, 142),
  (13239, 144),
  (4987, 144),
  (3957, 144),
  (3630, 144),
  (8625, 144),
  (499, 145),
  (406, 145),
  (768, 145),
  (614, 145),
  (1913, 145),
  (245, 146),
  (364, 146),
  (955, 146),
  (14425, 146),
  (406, 147),
  (640, 147),
  (614, 147),
  (499, 147),
  (126, 147),
  (14400, 148),
  (13963, 148),
  (14143, 149),
  (227, 149),
  (13749, 149),
  (13824, 149),
  (7920, 149),
  (1087, 150),
  (221, 150),
  (455, 151),
  (4296, 151),
  (10554, 151),
  (6893, 151),
  (6551, 151),
  (14131, 152),
  (14132, 152),
  (6734, 152),
  (9687, 152),
  (2256, 152),
  (996, 153),
  (554, 153),
  (2256, 153),
  (4601, 153),
  (2255, 153),
  (6191, 154),
  (7174, 154),
  (7248, 154),
  (13239, 154),
  (7865, 154),
  (12692, 155),
  (8220, 155),
  (9623, 155),
  (14232, 155),
  (13737, 155),
  (1275, 156),
  (648, 156),
  (520, 156),
  (1263, 156),
  (5653, 156),
  (2529, 157),
  (1913, 157),
  (1072, 157),
  (14301, 157),
  (14400, 157),
  (245, 158),
  (355, 158),
  (364, 158),
  (142, 158),
  (11052, 159),
  (1231, 159),
  (7516, 159),
  (13815, 160),
  (13706, 160),
  (6191, 160),
  (7174, 160),
  (13239, 160),
  (245, 161),
  (1224, 161),
  (137, 161),
  (955, 161),
  (364, 161),
  (3485, 162),
  (12930, 162),
  (1399, 162),
  (13825, 162),
  (7920, 162),
  (1087, 163),
  (459, 163),
  (1332, 163),
  (1315, 163),
  (1913, 164),
  (13930, 164),
  (14400, 164),
  (2643, 164),
  (13929, 164),
  (13825, 165),
  (13824, 165),
  (12930, 165),
  (227, 165),
  (11709, 165),
  (899, 166),
  (4645, 166),
  (199, 166),
  (5486, 167),
  (1913, 167),
  (6704, 167),
  (2529, 167),
  (10257, 167),
  (364, 168),
  (13749, 169),
  (14409, 169),
  (1399, 169),
  (9607, 169),
  (11709, 169),
  (459, 170),
  (1062, 170),
  (285, 170),
  (1357, 170),
  (6850, 171),
  (107, 171),
  (9850, 171),
  (12287, 171),
  (7834, 171),
  (1062, 172),
  (285, 172),
  (13834, 172),
  (13110, 172),
  (1087, 173),
  (221, 173),
  (459, 173),
  (6269, 174),
  (5707, 174),
  (10172, 174),
  (11052, 175),
  (849, 175),
  (1224, 176),
  (107, 176),
  (6850, 176),
  (603, 176),
  (6171, 176),
  (1062, 177),
  (13716, 177),
  (13834, 177),
  (8663, 177),
  (285, 177),
  (245, 178),
  (1224, 178),
  (9850, 178),
  (6987, 178),
  (12066, 178),
  (11545, 179),
  (1229, 179),
  (10101, 179),
  (3267, 179),
  (9542, 179),
  (955, 180),
  (364, 180),
  (137, 180),
  (107, 181),
  (12879, 181),
  (1224, 181),
  (6850, 181),
  (419, 181),
  (11461, 182),
  (10229, 182),
  (3266, 182),
  (3584, 182),
  (1303, 182),
  (13886, 183),
  (14031, 183),
  (13675, 183),
  (2576, 183),
  (2328, 183),
  (7827, 184),
  (4968, 184),
  (14140, 184),
  (7174, 184),
  (3324, 184),
  (1062, 185),
  (14153, 185),
  (5062, 185),
  (2381, 186),
  (2344, 186),
  (1931, 186),
  (2230, 186),
  (11672, 186),
  (3485, 187),
  (1399, 187),
  (13825, 187),
  (14420, 187),
  (13035, 187),
  (13886, 188),
  (13885, 188),
  (1770, 188),
  (1913, 188),
  (14031, 188),
  (12506, 189),
  (11672, 189),
  (2381, 189),
  (4925, 189),
  (4101, 189),
  (1342, 190),
  (103, 190),
  (9096, 190),
  (11874, 190),
  (11754, 191),
  (14193, 191),
  (14174, 191),
  (1157, 191),
  (1124, 191),
  (5839, 192),
  (8683, 192),
  (7683, 192),
  (13886, 193),
  (1913, 193),
  (14400, 193),
  (12410, 193),
  (2643, 193),
  (10579, 194),
  (13815, 194),
  (3701, 194),
  (7248, 194),
  (8625, 194),
  (13815, 195),
  (10579, 195),
  (13239, 195),
  (8625, 195),
  (6191, 195),
  (1062, 196),
  (8663, 196),
  (13110, 196),
  (6553, 196),
  (3204, 196),
  (11741, 197),
  (454, 197),
  (13239, 198),
  (13815, 198),
  (10579, 198),
  (8625, 198),
  (4987, 198),
  (245, 199),
  (355, 199),
  (5, 199),
  (6987, 199),
  (3838, 200),
  (13239, 201),
  (10973, 201),
  (3957, 201),
  (6191, 201),
  (7174, 201),
  (520, 202),
  (1275, 202),
  (1263, 202),
  (257, 202),
  (648, 202),
  (13239, 203),
  (6191, 203),
  (7248, 203),
  (7174, 203),
  (3957, 203),
  (14400, 204),
  (1913, 204),
  (499, 204),
  (2643, 204),
  (13886, 204),
  (700, 205),
  (2403, 205),
  (6651, 205),
  (2600, 205),
  (2496, 205),
  (14218, 206),
  (15, 206),
  (1191, 206),
  (157, 206),
  (483, 206),
  (13815, 207),
  (12492, 207),
  (7248, 207),
  (8625, 207),
  (13239, 207),
  (3212, 208),
  (4013, 208),
  (2381, 208),
  (11672, 208),
  (3005, 208),
  (10071, 209),
  (267, 209),
  (8220, 209),
  (10805, 209),
  (12692, 209),
  (267, 210),
  (10071, 210),
  (10805, 210),
  (14230, 210),
  (8485, 210),
  (520, 211),
  (1275, 211),
  (1263, 211),
  (6270, 211),
  (371, 211),
  (107, 212),
  (6850, 212),
  (12879, 212),
  (9850, 212),
  (6171, 212),
  (390, 213),
  (4296, 213),
  (14187, 213),
  (654, 214),
  (1913, 214),
  (499, 214),
  (2529, 214),
  (14400, 214),
  (264, 215),
  (13779, 215),
  (1153, 215),
  (642, 215),
  (225, 215),
  (13825, 216),
  (14420, 216),
  (7920, 216),
  (13824, 216),
  (4770, 216),
  (1087, 217),
  (364, 217),
  (1275, 218),
  (5653, 218),
  (4092, 218),
  (3604, 218),
  (9688, 218),
  (14232, 219),
  (8220, 219),
  (14400, 220),
  (1913, 220),
  (2643, 220),
  (126, 220),
  (1149, 220),
  (499, 221),
  (1913, 221),
  (4871, 221),
  (14400, 221),
  (13930, 221),
  (1087, 222),
  (221, 222),
  (459, 223),
  (531, 223),
  (1087, 224),
  (1315, 224),
  (221, 224),
  (1332, 224),
  (8220, 225),
  (107, 226),
  (6850, 226),
  (245, 226),
  (7834, 226),
  (13825, 227),
  (13824, 227),
  (10101, 227),
  (13749, 227),
  (3757, 227),
  (13886, 228),
  (2060, 228),
  (3001, 228),
  (2529, 228),
  (1696, 228),
  (1275, 229),
  (172, 229),
  (520, 229),
  (13714, 229),
  (648, 229),
  (1275, 230),
  (520, 230),
  (3604, 230),
  (5653, 230),
  (9688, 230),
  (1224, 231),
  (245, 231),
  (364, 231),
  (137, 231),
  (955, 231),
  (14260, 232),
  (14259, 232),
  (13886, 232),
  (6651, 232),
  (13657, 232),
  (1224, 233),
  (245, 233),
  (107, 233),
  (12879, 233),
  (603, 233),
  (6191, 234),
  (237, 234),
  (7248, 234),
  (3701, 234),
  (13706, 234),
  (459, 235),
  (1332, 235),
  (257, 236),
  (10805, 237),
  (14232, 237),
  (6789, 237),
  (6947, 238),
  (4467, 238),
  (7563, 238),
  (8753, 238),
  (11880, 238),
  (1275, 239),
  (13751, 239),
  (6518, 239),
  (13750, 239),
  (9980, 239),
  (533, 240),
  (2269, 240),
  (5486, 241),
  (11330, 241),
  (13885, 241),
  (2865, 241),
  (14400, 242),
  (1913, 242),
  (2643, 242),
  (13886, 242),
  (12410, 242),
  (14400, 244),
  (1913, 244),
  (2643, 244),
  (12410, 244),
  (7390, 244),
  (878, 246),
  (607, 246),
  (53, 246),
  (173, 246),
  (12974, 246),
  (459, 247),
  (607, 247),
  ...])
In [85]:
from celligner.params import TISSUE_COLOR
In [97]:
my_alligner.plot(color_column="tissue_type", colortable=TISSUE_COLOR)
reducing dimensionality...
making plot...
Out[97]:
Figure(
id = '3591', …)
In [ ]: